Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    evaluations of worth and value in decisions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    assessing if something is worth it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étranger
    -0.41
     ainfi
    -0.39
     dAtA
    -0.39
     vectorielles
    -0.38
    有一天
    -0.38
    ScopeManager
    -0.37
     ayudado
    -0.37
     pouvoit
    -0.36
     rå
    -0.35
     ſol
    -0.35
    POSITIVE LOGITS
     worth
    0.77
     Worth
    0.74
    Worth
    0.70
     worthwhile
    0.64
     WORTH
    0.64
    worth
    0.63
    值得
    0.60
     lohnt
    0.59
    WORTH
    0.55
     Worthy
    0.50
    Act Density 0.104%

    No Known Activations